Learning and relearning in Boltzmann machines

By Geoffrey E. Hinton, Terrence J. Sejnowski. 1986

Subfields: Reinforcement Learning, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

In Probabilistic & Bayesian Methods

Citations in the corpus

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (2016, methodology): “A family of popular probabilistic models is the Restricted Boltzmann Machine (RBM) [32,16], which makes training tractable by imposing a bipartite graph between latent and observed variables.”
Generating Images with Perceptual Similarity Metrics based on Deep Networks (2016, background): “A prominent class of probabilistic models of images are restricted Boltzmann machines (Hinton & Sejnowski, 1986; Smolensky, 1987; Hinton & Salakhut-dinov, 2006) and their deep variants (Hinton et al., 2006; Salakhutdinov & Hinton, 2009; Lee et al., 2009).”
NIPS 2016 Tutorial: Generative Adversarial Networks (2016, background): “Boltzmann machines (Fahlman et al., 1983; Ackley et al., 1985; Hinton et al., 1984; Hinton and Sejnowski, 1986) are a family of generative models that rely on Markov chains both to train the model or to generate a sample from the model.”
Deep learning in neural networks: An overview (2014, background): “The Deep Belief Network (DBN) is a stack of Restricted Boltzmann Machines (RBMs) (Smolensky, 1986), which in turn are Boltzmann Machines (BMs) (Hinton & Sejnowski, 1986) with a single layer of feature-detecting units; compare also Higher-Order BMs (Memisevic & Hinton, 2010).”
How to Represent Part-Whole Hierarchies in a Neural Network (2021, neutral): “Hinton and Sejnowski [Hinton and Sejnowski, 1986] even suggested that sleep could be used for following the derivatives of the normalizing term in the negative phase of Boltzmann machine learning.”
Hierarchical Mixtures of Experts and the EM Algorithm (1993, methodology): “The Boltzmann learning algorithm (Hinton & Sejnowski, 1986) is a neural network example of a GEM algorithm.”
Deep Energy Estimator Networks (2018, background): “This quest has a rich history, going back to the Boltzmann machine at the birth of the connectionist movement (Hinton & Sejnowski, 1986), but an efﬁcient, robust, and general-purpose method for continuous-valued data is still missing.”
Learning Temporal Transformations from Time-Lapse Videos (2016, background): “Image/Frame generation: Generative models have attracted extensive attention in machine learning [16,17,18,19,20,21].”
Deep Learning for Health Informatics (2017, background): “A RBM was first proposed in [37] and is a variant of the Boltzmann machine, which is a type of stochastic NN.”
Stochastic interactive processes and the effect of context on perception. (1991, methodology): “…involves replacing the dynamical assumptions of interactive activation networks with the dynamical assumptions used in the Boltzmann machine (Hinton & Sejnowski, 1983, 1986).5 Boltzmann machines and stochastic interactive activation networks of the type considered thus far share several key…”
Semantic Cognition: A Parallel Distributed Processing Approach (2004, background): “Murphy and Medin (1985) and others have suggested that the challenge of selecting and weighting features appropriately might be resolved with reference to naive theories about the causal relationship among object properties.”
The Visual System's Internal Model of the World (2015, methodology): “[18] G.”
Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons (2011, methodology): “There are a number of studies proposing neural network architectures that implement probabilistic inference [15,17,18,35– 48].”
The Forward-Forward Algorithm: Some Preliminary Investigations (2022, methodology): “The original Boltzmann Machine learning algorithm was designed to avoid this flaw (Hinton and Sejnowski, 1986) (page 297) by contrasting statistics caused by two different external boundary conditions.”
Ising models for networks of real neurons (2006, methodology): “For larger systems, this “inverse Ising problem” or Boltzmann machine learning, as it is known in computer science [11], is a hard computational problem rarely encountered in physics, where we usually compute properties of the system given a known model of the interactions.”